American Express Travel Related Services Company, Inc.

Nfl Enterprises LLC

Iwao Fusillo

Rajendra R Rane

Mehmet E Dedeoglu

David Juang

Karlyn Heiner Crotty

Prashant Kalia

Eduardo J Alvarez

Andrew Roth

Eddie J Alvarez

Qaiser S Shakeel

Lewis A Tierney

Danny M Yelle

David Samuel Highhill

Justin Friedman

Adriane Beth Berman

Robert Joseph Yang

Nitish Basandra

A system, method, and computer readable storage media for training a model to estimate an unknown consumer behavior while preserving consumer privacy by combining a first training data set of a first organization with a second training data set of a second organization on a third-party computer system, wherein the second training data set contains an attribute value the first organization wishes to estimate, and wherein the first organization cannot access the third-party computing system, providing a trainable model definition to the third-party computer, training the model, and returning the trained computer model.

Systems and methods for privacy-preserving generation of models for estimating consumer behavior

A third party facilitates exchange of customer data between first and second entities while maintaining customer privacy. Personally identifiable information (PII) and first entity customer attributes of a first set of customers are received from a first entity. PII for a second set of customers is received from a second entity. First and second set common customers are identified using the PII of the first and the second set of customers. Subsequently, a list of third set of customers is sent to the second entity. The list of third set of customers includes the common customers and a plurality of other customers from the second set of customers. Second entity customer attributes are received for each customer in the list of third set of customers. Further, the first entity customer attributes of the common customers and the second entity customer attributes of the common customers are linked.

Anonymous information exchange

The present disclosure includes a system, method, and article of manufacture for spend based targeting and measurement. The method may comprise transmitting to a third party system a model and/or a measurement file associating a first party cookie ID with a model, and receiving, from the third party system, an updated model (and/or measurement) file associating a third party cookie ID with web-browsing data. The third party cookie ID may anonymously and uniquely correspond to the first party cookie ID, and the first party cookie ID may be stripped from the updated model (and/or measurement) file to de-identify a customer associated with the first party cookie ID. Moreover, the web-browsing data may be received by the third party system from a second party system.

Spend based digital ad targeting and measurement

A method and computer program product for identifying attributes of customers and potential customers, allowing marketing to be directed at such consumers. Information is received regarding each of a number of consumers. This information can include demographic information, data regarding spending habits, and information as to how such attributes may have changed over time. Once attributes have been determined, and any changes over time to such attributes have been determined, a correlation of the attributes is performed. Such combined attributes are denoted as composite dimensions. Given the composite dimensions, as well as attributes that may not have been correlated with any other attributes, consumers are plotted in the resulting multi-dimensional space. Sets of consumers that appear to be grouped in this multi-dimensional space are then identified. Common attributes of this consumer group are identified. Unique attributes of a given consumer in such a group are also identified.

Multidimensional personal behavioral tomography

According to embodiments of the present invention there is provided a computer-based method and a computer program product for automatically sorting customers who make purchases from merchants using a credit card. The computer-based method includes the following steps. An adjusted index is calculated for a customer based on an amount of money the customer spent across merchants during a time period. The adjusted index is compared to a cut-off value. The customer is classified based on the comparison of the adjusted index to the cut-off value. In an embodiment, the method also includes re-classifying the customer based on at least one of (i) information about the merchants, or (ii) a number of transactions in a predetermined industry.

Automatic classification of credit card customers

Consumer spend by industry is modeled based on the industry sizes of wallet of consumers having a high share of wallet with a financial institution. A size of wallet is calculated for each consumer in a plurality of consumers. A share of wallet for each consumer is also calculated. A subset of the plurality of consumers whose share of wallet is above a given percentage of their size of wallet is then determined. For each consumer in the subset, an industry size of wallet is determined. A correlation between the industry size of wallet of a given consumer and one or more characteristics of the given consumer is then derived using the industry size of wallet for the consumers in the subset.

Industry size of wallet

Growing community of inventors

Merrick, NY, United States of America

Iwao Fusillo